Mongod intermittently consuming all available CPU.

XMLWordPrintableJSON

    • Type: Bug
    • Resolution: Done
    • Priority: Major - P3
    • None
    • Affects Version/s: None
    • Component/s: Admin
    • None
    • ALL
    • None
    • None
    • None
    • None
    • None
    • None
    • None

      This is a new issue with a deployment created with Cloud Manager. The server was provisioned on AWS through CM's provisioning tool. It was added to a replica set as secondary so that the old primary could subsequently be shut down. I've noticed that once every ~7 seconds, mongod will consume all CPU for about ~10 seconds. I will attach logs of mongostat, iostat & db.serverStatus() during and after a spike.

        1. iostat.log
          16 kB
        2. mongostat.log
          11 kB
        3. serverStatusAfter.log
          18 kB
        4. serverStatusDuring.log
          18 kB
        5. diagnostic.data.tgz
          12.03 MB
        6. findAndModify_workload.png
          findAndModify_workload.png
          23 kB
        7. iostat2.log
          360 kB
        8. mongostat2.log
          38 kB
        9. iostat3.log
          343 kB
        10. ss.log
          6.18 MB
        11. findAndModify_workload_mmapv1.png
          findAndModify_workload_mmapv1.png
          60 kB

            Assignee:
            Kelsey Schubert
            Reporter:
            Zachary Rollyson
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

              Created:
              Updated:
              Resolved: